{"id":"https://openalex.org/W7125943623","doi":"https://doi.org/10.1145/3774934.3786461","title":"ROME: Maximizing GPU Efficiency for All-Pairs Shortest Path via Taming Fine-Grained Irregularities","display_name":"ROME: Maximizing GPU Efficiency for All-Pairs Shortest Path via Taming Fine-Grained Irregularities","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7125943623","doi":"https://doi.org/10.1145/3774934.3786461"},"language":null,"primary_location":{"id":"doi:10.1145/3774934.3786461","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774934.3786461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104247871","display_name":"Weile Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Weile Luo","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040753937","display_name":"Yuhan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhan Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101297034","display_name":"Xiangrui Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangrui Yu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124069122","display_name":"Qiang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054056254","display_name":"Ruibo Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruibo Fan","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079275912","display_name":"Hongyuan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongyuan Liu","raw_affiliation_strings":["Stevens Institute of Technology, Hoboken, USA"],"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology, Hoboken, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaowen Chu","orcid":"https://orcid.org/0000-0001-9745-4372"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaowen Chu","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong","The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5104247871"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23631033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"204","last_page":"217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9531000256538391,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9531000256538391,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.010200000368058681,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.005799999926239252,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.9027000069618225},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.619700014591217},{"id":"https://openalex.org/keywords/shortest-path-problem","display_name":"Shortest path problem","score":0.6080999970436096},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5665000081062317},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5443000197410583},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5013999938964844},{"id":"https://openalex.org/keywords/vertex","display_name":"Vertex (graph theory)","score":0.49729999899864197},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.44850000739097595}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.9027000069618225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817000150680542},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.72079998254776},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.619700014591217},{"id":"https://openalex.org/C22590252","wikidata":"https://www.wikidata.org/wiki/Q1058754","display_name":"Shortest path problem","level":3,"score":0.6080999970436096},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5665000081062317},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5443000197410583},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C80899671","wikidata":"https://www.wikidata.org/wiki/Q1304193","display_name":"Vertex (graph theory)","level":3,"score":0.49729999899864197},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.44850000739097595},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3993000090122223},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.320499986410141},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C2986651925","wikidata":"https://www.wikidata.org/wiki/Q1514868","display_name":"Graph algorithms","level":3,"score":0.29269999265670776},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.2766000032424927},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774934.3786461","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774934.3786461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1039385342","https://openalex.org/W1695070436","https://openalex.org/W1980153429","https://openalex.org/W1985291160","https://openalex.org/W1997162567","https://openalex.org/W2000041758","https://openalex.org/W2004951603","https://openalex.org/W2007572995","https://openalex.org/W2034102265","https://openalex.org/W2057112598","https://openalex.org/W2067976091","https://openalex.org/W2104734478","https://openalex.org/W2107173440","https://openalex.org/W2113679823","https://openalex.org/W2117758387","https://openalex.org/W2120424341","https://openalex.org/W2127144731","https://openalex.org/W2137541800","https://openalex.org/W2169528473","https://openalex.org/W2494056327","https://openalex.org/W2502734103","https://openalex.org/W2523378841","https://openalex.org/W2581090187","https://openalex.org/W2582905775","https://openalex.org/W2788517652","https://openalex.org/W2790789009","https://openalex.org/W2887905332","https://openalex.org/W2915012400","https://openalex.org/W2951135776","https://openalex.org/W3000173590","https://openalex.org/W3130678148","https://openalex.org/W3138165103","https://openalex.org/W4232836277","https://openalex.org/W4316252357","https://openalex.org/W4381327291","https://openalex.org/W7106695908"],"related_works":[],"abstract_inverted_index":{"All-Pairs":[0],"Shortest":[1],"Path":[2],"(APSP),":[3],"a":[4,43],"fundamental":[5],"problem":[6],"in":[7],"graph":[8],"analytics,":[9],"can":[10],"be":[11],"solved":[12],"efficiently":[13],"by":[14,49],"reducing":[15],"the":[16,69,78],"computational":[17],"workload":[18],"through":[19],"vertex":[20],"reordering.":[21],"However,":[22],"it":[23],"fails":[24],"on":[25],"GPUs":[26],"due":[27],"to":[28,91],"fine-grained":[29],"granularity,":[30],"shape,":[31],"and":[32,56,74,89],"dependency":[33],"irregularities,":[34],"which":[35],"cause":[36],"severe":[37],"hardware":[38],"underutilization.":[39],"We":[40],"introduce":[41],"ROME,":[42],"system":[44],"that":[45],"tames":[46],"these":[47],"irregularities":[48],"spatially":[50],"restructuring":[51],"computation":[52],"into":[53],"regularized":[54],"workloads":[55],"temporally":[57],"overlapping":[58],"them":[59],"with":[60],"an":[61],"asynchronous":[62],"pipeline.":[63],"ROME":[64],"achieves":[65],"14.7-244.5\u00d7":[66],"speedup":[67,76],"over":[68,77],"state-of-the-art":[70,79],"multicore":[71],"CPU":[72],"solution":[73],"11.2-338.0\u00d7":[75],"GPU":[80],"solution.":[81],"Notably,":[82],"our":[83],"results":[84],"achieve":[85],"mostly":[86],"above":[87],"20%":[88],"up":[90],"34.7%":[92],"of":[93],"peak":[94],"min-plus":[95],"OPs":[96],"across":[97],"all":[98],"tested":[99],"graphs.":[100]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-29T00:00:00"}